Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes?
arXiv:2609.32495v1 Announce Type: cross Abstract: An agent harness, the code that turns a model into an agent, writes its own record of each run, and that record is all a later reader gets when a run is disputed, investigated or audited. We call a record evide
arXiv cs.AIResearch source·